Update app.py

app.py

@@ -1,89 +1,111 @@
-# app.py
-from fastapi import FastAPI
-from pydantic import BaseModel
-from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
-import torch
-
-app = FastAPI(title="Forex Sentiment API", version="1.0")
-
-# ===============================
-# Load Models
-# ===============================
-finbert_name = "ProsusAI/finbert"
-longformer_name = "Miruzen/LongFormer_Skripsi"
-
-device = 0 if torch.cuda.is_available() else -1
-
-print("📥 Loading FinBERT model...")
-finbert = pipeline("text-classification",
-                    model=finbert_name,
-                    tokenizer=finbert_name,
-                    return_all_scores=True,
-                    device=device)
-
-print("📥 Loading LongFormer model...")
-longformer = pipeline("text-classification",
-                        model=longformer_name,
-                        tokenizer=longformer_name,
-                        return_all_scores=True,
-                        device=device)
-
-# ===============================
-# Input Schema
-# ===============================
-class InputData(BaseModel):
-    title: str | None = None
-    content: str | None = None
-
-
-# ===============================
-# Helper Functions
-# ===============================
-def extract_scores(predictions):
-    """Convert HF model output into {positive, neutral, negative} dict."""
-    scores = {"positive": 0.0, "neutral": 0.0, "negative": 0.0}
-    for item in predictions[0]:
-        label = item["label"].lower()
-        if "pos" in label:
-            scores["positive"] = item["score"]
-        elif "neg" in label:
-            scores["negative"] = item["score"]
-        elif "neu" in label:
-            scores["neutral"] = item["score"]
-    dominant = max(scores, key=scores.get)
-    return {"label": dominant, "scores": scores}
-
-
-# ===============================
-# Main Endpoint
-# ===============================
-@app.post("/analyze")
-def analyze(data: InputData):
-    result = {}
-
-    if data.title:
-        finbert_out = finbert(data.title)
-        result["title"] = extract_scores(finbert_out)
-
-    if data.content:
-        longformer_out = longformer(data.content)
-        result["content"] = extract_scores(longformer_out)
-
-    # Gabungkan menjadi mood_score sederhana
-    mood_score = (
-        result.get("title", {}).get("scores", {}).get("positive", 0)
-        + result.get("content", {}).get("scores", {}).get("positive", 0)
-        - result.get("title", {}).get("scores", {}).get("negative", 0)
-        - result.get("content", {}).get("scores", {}).get("negative", 0)
-    )
-
-    return {
-        "mood_score": mood_score,
-        "details": result,
-        "status": "ok"
-    }
-
-
-@app.get("/")
-def root():
-    return {"message": "Forex Sentiment API active!"}
+from fastapi import FastAPI
+from pydantic import BaseModel
+import requests
+import os
+
+app = FastAPI(title="Forex Sentiment API", version="2.0")
+
+# ===============================
+# Konfigurasi
+# ===============================
+HF_ROUTER_URL = "https://router.huggingface.co/hf-inference/models"
+HF_API_KEY = os.getenv("HF_API_KEY")
+
+FINBERT_MODEL = "ProsusAI/finbert"
+LONGFORMER_MODEL = "Miruzen/LongFormer_Skripsi"
+
+
+# ===============================
+# Input Schema
+# ===============================
+class InputData(BaseModel):
+    title: str | None = None
+    content: str | None = None
+
+
+# ===============================
+# Helper Functions
+# ===============================
+def call_hf_model(model_name: str, text: str):
+    """Kirim teks ke model Hugging Face menggunakan router API baru"""
+    headers = {
+        "Authorization": f"Bearer {HF_API_KEY}",
+        "Content-Type": "application/json",
+    }
+
+    payload = {
+        "inputs": text,
+        "options": {"wait_for_model": True}
+    }
+
+    url = f"{HF_ROUTER_URL}/{model_name}"
+    response = requests.post(url, headers=headers, json=payload)
+
+    if response.status_code != 200:
+        raise Exception(
+            f"HF API error ({response.status_code}): {response.text}"
+        )
+
+    return response.json()
+
+
+def extract_scores(predictions):
+    """Convert HF model output into {positive, neutral, negative} dict."""
+    scores = {"positive": 0.0, "neutral": 0.0, "negative": 0.0}
+
+    # Router API sometimes returns either list of lists or single list
+    data = predictions[0] if isinstance(predictions, list) else predictions
+    if isinstance(data, list) and len(data) > 0 and isinstance(data[0], dict):
+        for item in data:
+            label = item.get("label", "").lower()
+            if "pos" in label:
+                scores["positive"] = item["score"]
+            elif "neg" in label:
+                scores["negative"] = item["score"]
+            elif "neu" in label:
+                scores["neutral"] = item["score"]
+
+    dominant = max(scores, key=scores.get)
+    return {"label": dominant, "scores": scores}
+
+
+# ===============================
+# Main Endpoint
+# ===============================
+@app.post("/analyze")
+def analyze(data: InputData):
+    result = {}
+    errors = []
+
+    if data.title:
+        try:
+            finbert_out = call_hf_model(FINBERT_MODEL, data.title)
+            result["title"] = extract_scores(finbert_out)
+        except Exception as e:
+            errors.append(f"Title analysis error: {e}")
+
+    if data.content:
+        try:
+            longformer_out = call_hf_model(LONGFORMER_MODEL, data.content)
+            result["content"] = extract_scores(longformer_out)
+        except Exception as e:
+            errors.append(f"Content analysis error: {e}")
+
+    mood_score = (
+        result.get("title", {}).get("scores", {}).get("positive", 0)
+        + result.get("content", {}).get("scores", {}).get("positive", 0)
+        - result.get("title", {}).get("scores", {}).get("negative", 0)
+        - result.get("content", {}).get("scores", {}).get("negative", 0)
+    )
+
+    return {
+        "mood_score": mood_score,
+        "details": result,
+        "errors": errors,
+        "status": "ok" if not errors else "partial"
+    }
+
+
+@app.get("/")
+def root():
+    return {"message": "Forex Sentiment API active via router.huggingface.co!"}